arXiv subjects

Swanand Kadhe

Publications and source records attributed to Swanand Kadhe.

At least 19 recordsLinked to original sources

arXiv2026

AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows

Agentic systems are increasingly acting on users' behalf, accessing calendars, email, and personal files to complete everyday tasks. Privacy evaluation for these systems has focused on the input and output boundaries, but each task involves several intermediate information flows, from agent queries to tool responses, that are not currently evaluated. We argue that every boundary in an agentic pipeline is a site of potential privacy violation and must be assessed independently. To support this, we introduce the Privacy Flow Graph, a Contextual Integrity-grounded framework that decomposes agentic execution into a sequence of information flows, each annotated with the five CI parameters, and traces violations to their point of origin. We present AgentSCOPE, a benchmark of 62 multi-tool scenarios across eight regulatory domains with ground truth at every pipeline stage. Our evaluation across seven state-of-the-art LLMs show that privacy violations in the pipeline occur in over 80% of scenarios, even when final outputs appear clean (24%), with most violations arising at the tool-response stage where APIs return sensitive data indiscriminately. These results indicate that output-level evaluation alone substantially underestimates the privacy risk of agentic systems.

cs.CR↗

arXiv2025

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents

Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents-such as large language models (LLMs)-their private information becomes vulnerable to exposure. In this paper, we characterize the notion of contextual privacy for user interactions with LLM-based Conversational Agents (LCAs). It aims to minimize privacy risks by ensuring that users (sender) disclose only information that is both relevant and necessary for achieving their intended goals when interacting with LCAs (untrusted receivers). Through a formative design user study, we observe how even "privacy-conscious" users inadvertently reveal sensitive information through indirect disclosures. Based on insights from this study, we propose a locally deployable framework that operates between users and LCAs, identifying and reformulating out-of-context information in user prompts. Our evaluation using examples from ShareGPT shows that lightweight models can effectively implement this framework, achieving strong gains in contextual privacy while preserving the user's intended interaction goals. Notably, about 76% of participants in our human evaluation preferred the reformulated prompts over the original ones, validating the usability and effectiveness of contextual privacy in our proposed framework. We opensource the code at https://github.com/IBM/contextual-privacy-LLM.

cs.CR↗

arXiv2025

Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on performance metrics such as AUC, accuracy, and TPR@low FPR - either by developing new methods to enhance these metrics or using them to evaluate privacy solutions - we found that it overlooks the disparities among different attacks. These disparities, both between distinct attack methods and between multiple instantiations of the same method, have crucial implications for the reliability and completeness of MIAs as privacy evaluation tools. In this paper, we systematically investigate these disparities through a novel framework based on coverage and stability analysis. Extensive experiments reveal significant disparities in MIAs, their potential causes, and their broader implications for privacy evaluation. To address these challenges, we propose an ensemble framework with three distinct strategies to harness the strengths of state-of-the-art MIAs while accounting for their disparities. This framework not only enables the construction of more powerful attacks but also provides a more robust and comprehensive methodology for privacy evaluation.

cs.LG↗

arXiv2025

Towards a Re-evaluation of Data Forging Attacks in Practice

Data forging attacks provide counterfactual proof that a model was trained on a given dataset, when in fact, it was trained on another. These attacks work by forging (replacing) mini-batches with ones containing distinct training examples that produce nearly identical gradients. Data forging appears to break any potential avenues for data governance, as adversarial model owners may forge their training set from a dataset that is not compliant to one that is. Given these serious implications on data auditing and compliance, we critically analyse data forging from both a practical and theoretical point of view, finding that a key practical limitation of current attack methods makes them easily detectable by a verifier; namely that they cannot produce sufficiently identical gradients. Theoretically, we analyse the question of whether two distinct mini-batches can produce the same gradient. Generally, we find that while there may exist an infinite number of distinct mini-batches with real-valued training examples and labels that produce the same gradient, finding those that are within the allowed domain e.g. pixel values between 0-255 and one hot labels is a non trivial task. Our results call for the reevaluation of the strength of existing attacks, and for additional research into successful data forging, given the serious consequences it may have on machine learning and privacy.

cs.CR↗

arXiv2023

Federated Unlearning: How to Efficiently Erase a Client in FL?

With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its training data. However, existing unlearning methods in the machine learning context can not be directly applied in the context of distributed settings like federated learning due to the differences in learning protocol and the presence of multiple actors. In this paper, we tackle the problem of federated unlearning for the case of erasing a client by removing the influence of their entire local data from the trained global model. To erase a client, we propose to first perform local unlearning at the client to be erased, and then use the locally unlearned model as the initialization to run very few rounds of federated learning between the server and the remaining clients to obtain the unlearned global model. We empirically evaluate our unlearning method by employing multiple performance measures on three datasets, and demonstrate that our unlearning method achieves comparable performance as the gold standard unlearning method of federated retraining from scratch, while being significantly efficient. Unlike prior works, our unlearning method neither requires global access to the data used for training nor the history of the parameter updates to be stored by the server or any of the clients.

cs.LG↗

arXiv2023

LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning

We propose LESS-VFL, a communication-efficient feature selection method for distributed systems with vertically partitioned data. We consider a system of a server and several parties with local datasets that share a sample ID space but have different feature sets. The parties wish to collaboratively train a model for a prediction task. As part of the training, the parties wish to remove unimportant features in the system to improve generalization, efficiency, and explainability. In LESS-VFL, after a short pre-training period, the server optimizes its part of the global model to determine the relevant outputs from party models. This information is shared with the parties to then allow local feature selection without communication. We analytically prove that LESS-VFL removes spurious features from model training. We provide extensive empirical evidence that LESS-VFL can achieve high accuracy and remove spurious features at a fraction of the communication cost of other feature selection approaches.

cs.LG↗

arXiv2022

Robust Learning Protocol for Federated Tumor Segmentation Challenge

In this work, we devise robust and efficient learning protocols for orchestrating a Federated Learning (FL) process for the Federated Tumor Segmentation Challenge (FeTS 2022). Enabling FL for FeTS setup is challenging mainly due to data heterogeneity among collaborators and communication cost of training. To tackle these challenges, we propose Robust Learning Protocol (RoLePRO) which is a combination of server-side adaptive optimisation (e.g., server-side Adam) and judicious parameter (weights) aggregation schemes (e.g., adaptive weighted aggregation). RoLePRO takes a two-phase approach, where the first phase consists of vanilla Federated Averaging, while the second phase consists of a judicious aggregation scheme that uses a sophisticated reweighting, all in the presence of an adaptive optimisation algorithm at the server. We draw insights from extensive experimentation to tune learning rates for the two phases.

cs.LG↗

arXiv2022

DeTrust-FL: Privacy-Preserving Federated Learning in Decentralized Trust Setting

Federated learning has emerged as a privacy-preserving machine learning approach where multiple parties can train a single model without sharing their raw training data. Federated learning typically requires the utilization of multi-party computation techniques to provide strong privacy guarantees by ensuring that an untrusted or curious aggregator cannot obtain isolated replies from parties involved in the training process, thereby preventing potential inference attacks. Until recently, it was thought that some of these secure aggregation techniques were sufficient to fully protect against inference attacks coming from a curious aggregator. However, recent research has demonstrated that a curious aggregator can successfully launch a disaggregation attack to learn information about model updates of a target party. This paper presents DeTrust-FL, an efficient privacy-preserving federated learning framework for addressing the lack of transparency that enables isolation attacks, such as disaggregation attacks, during secure aggregation by assuring that parties' model updates are included in the aggregated model in a private and secure manner. DeTrust-FL proposes a decentralized trust consensus mechanism and incorporates a recently proposed decentralized functional encryption (FE) scheme in which all parties agree on a participation matrix before collaboratively generating decryption key fragments, thereby gaining control and trust over the secure aggregation process in a decentralized setting. Our experimental evaluation demonstrates that DeTrust-FL outperforms state-of-the-art FE-based secure multi-party aggregation solutions in terms of training time and reduces the volume of data transferred. In contrast to existing approaches, this is achieved without creating any trust dependency on external trusted entities.

cs.CR↗

arXiv2021

Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation

We study the problem of estimating at a central server the mean of a set of vectors distributed across several nodes (one vector per node). When the vectors are high-dimensional, the communication cost of sending entire vectors may be prohibitive, and it may be imperative for them to use sparsification techniques. While most existing work on sparsified mean estimation is agnostic to the characteristics of the data vectors, in many practical applications such as federated learning, there may be spatial correlations (similarities in the vectors sent by different nodes) or temporal correlations (similarities in the data sent by a single node over different iterations of the algorithm) in the data vectors. We leverage these correlations by simply modifying the decoding method used by the server to estimate the mean. We provide an analysis of the resulting estimation error as well as experiments for PCA, K-Means and Logistic Regression, which show that our estimators consistently outperform more sophisticated and expensive sparsification methods.

cs.LG↗

arXiv2021

Logical Clifford Synthesis for Stabilizer Codes

Quantum error-correcting codes are used to protect qubits involved in quantum computation. This process requires logical operators, acting on protected qubits, to be translated into physical operators (circuits) acting on physical quantum states. We propose a mathematical framework for synthesizing physical circuits that implement logical Clifford operators for stabilizer codes. Circuit synthesis is enabled by representing the desired physical Clifford operator in $\mathbb{C}^{N \times N}$ as a partial $2m \times 2m$ binary symplectic matrix, where $N = 2^m$. We state and prove two theorems that use symplectic transvections to efficiently enumerate all binary symplectic matrices that satisfy a system of linear equations. As a corollary of these results, we prove that for an $[\![ m,k ]\!]$ stabilizer code every logical Clifford operator has $2^{r(r+1)/2}$ symplectic solutions, where $r = m-k$, up to stabilizer degeneracy. The desired physical circuits are then obtained by decomposing each solution into a product of elementary symplectic matrices, that correspond to elementary circuits. This enumeration of all physical realizations enables optimization over the ensemble with respect to a suitable metric. Furthermore, we show that any circuit that normalizes the stabilizer of the code can be transformed into a circuit that centralizes the stabilizer, while realizing the same logical operation. Our method of circuit synthesis can be applied to any stabilizer code, and this paper discusses a proof of concept synthesis for the $[\![ 6,4,2 ]\!]$ CSS code. Programs implementing the algorithms in this paper, which includes routines to solve for binary symplectic solutions of general linear systems and our overall LCS (logical circuit synthesis) algorithm, can be found at: https://github.com/nrenga/symplectic-arxiv18a

quant-ph↗

arXiv2021

Communication-Efficient and Byzantine-Robust Distributed Learning with Error Feedback

We develop a communication-efficient distributed learning algorithm that is robust against Byzantine worker machines. We propose and analyze a distributed gradient-descent algorithm that performs a simple thresholding based on gradient norms to mitigate Byzantine failures. We show the (statistical) error-rate of our algorithm matches that of Yin et al.~\cite{dong}, which uses more complicated schemes (coordinate-wise median, trimmed mean). Furthermore, for communication efficiency, we consider a generic class of $δ$-approximate compressors from Karimireddi et al.~\cite{errorfeed} that encompasses sign-based compressors and top-$k$ sparsification. Our algorithm uses compressed gradients and gradient norms for aggregation and Byzantine removal respectively. We establish the statistical error rate for non-convex smooth loss functions. We show that, in certain range of the compression factor $δ$, the (order-wise) rate of convergence is not affected by the compression operation. Moreover, we analyze the compressed gradient descent algorithm with error feedback (proposed in \cite{errorfeed}) in a distributed setting and in the presence of Byzantine worker machines. We show that exploiting error feedback improves the statistical error rate. Finally, we experimentally validate our results and show good performance in convergence for convex (least-square regression) and non-convex (neural network training) problems.

cs.LG↗

arXiv2021

Service Rate Region: A New Aspect of Coded Distributed System Design

Erasure coding has been recognized as a powerful method to mitigate delays due to slow or straggling nodes in distributed systems. This work shows that erasure coding of data objects can flexibly handle skews in the request rates. Coding can help boost the \emph{service rate region}, that is, increase the overall volume of data access requests that the system can handle. This paper aims to postulate the service rate region as an important consideration in the design of erasure-coded distributed systems. We highlight several open problems that can be grouped into two broad threads: 1) characterizing the service rate region of a given code and finding the optimal request allocation, and2) designing the underlying erasure code for a given service rate region. As contributions along the first thread, we characterize the rate regions of maximum-distance-separable, locally repairable, and Simplex codes. We show the effectiveness of hybrid codes that combine replication and erasure coding in terms of code design. We also discover fundamental connections between multi-set batch codes and the problem of maximizing the service rate region.

cs.IT↗

arXiv2021

Download Time Analysis for Distributed Storage Codes with Locality and Availability

The paper presents techniques for analyzing the expected download time in distributed storage systems that employ systematic availability codes. These codes provide access to hot data through the systematic server containing the object and multiple recovery groups. When a request for an object is received, it can be replicated (forked) to the systematic server and all recovery groups. We first consider the low-traffic regime and present the close-form expression for the download time. By comparison across systems with availability, maximum distance separable (MDS), and replication codes, we demonstrate that availability codes can reduce download time in some settings but are not always optimal. In the high-traffic regime, the system consists of multiple inter-dependent Fork-Join queues, making exact analysis intractable. Accordingly, we present upper and lower bounds on the download time, and an M/G/1 queue approximation for several cases of interest. Via extensive numerical simulations, we evaluate our bounds and demonstrate that the M/G/1 queue approximation has a high degree of accuracy.

cs.PF↗

arXiv2020

CoVer: Collaborative Light-Node-Only Verification and Data Availability for Blockchains

Validating a blockchain incurs heavy computation, communication, and storage costs. As a result, clients with limited resources, called light nodes, cannot verify transactions independently and must trust full nodes, making them vulnerable to security attacks. Motivated by this problem, we ask a fundamental question: can light nodes securely validate without any full nodes? We answer affirmatively by proposing CoVer, a decentralized protocol that allows a group of light nodes to collaboratively verify blocks even under a dishonest majority, achieving the same level of security for block validation as full nodes while only requiring a fraction of the work. In particular, work per node scales down proportionally with the number of participants (up to a log factor), resulting in computation, communication, and storage requirements that are sublinear in block size. Our main contributions are light-node-only protocols for fraud proofs and data availability.

cs.CR↗

arXiv2020

FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning

Recent attacks on federated learning demonstrate that keeping the training data on clients' devices does not provide sufficient privacy, as the model parameters shared by clients can leak information about their training data. A 'secure aggregation' protocol enables the server to aggregate clients' models in a privacy-preserving manner. However, existing secure aggregation protocols incur high computation/communication costs, especially when the number of model parameters is larger than the number of clients participating in an iteration -- a typical scenario in federated learning. In this paper, we propose a secure aggregation protocol, FastSecAgg, that is efficient in terms of computation and communication, and robust to client dropouts. The main building block of FastSecAgg is a novel multi-secret sharing scheme, FastShare, based on the Fast Fourier Transform (FFT), which may be of independent interest. FastShare is information-theoretically secure, and achieves a trade-off between the number of secrets, privacy threshold, and dropout tolerance. Riding on the capabilities of FastShare, we prove that FastSecAgg is (i) secure against the server colluding with 'any' subset of some constant fraction (e.g. $\sim10\%$) of the clients in the honest-but-curious setting; and (ii) tolerates dropouts of a 'random' subset of some constant fraction (e.g. $\sim10\%$) of the clients. FastSecAgg achieves significantly smaller computation cost than existing schemes while achieving the same (orderwise) communication cost. In addition, it guarantees security against adaptive adversaries, which can perform client corruptions dynamically during the execution of the protocol.

cs.CR↗

arXiv2020

Stealthy Communication over Adversarially Jammed Multipath Networks

We consider the problem of stealthy communication over a multipath network in the presence of an active adversary. The multipath network consists of multiple parallel noiseless links, and the adversary is able to eavesdrop and jam a subset of links. We consider two types of jamming---erasure jamming and overwrite jamming. We require the communication to be both stealthy and reliable, i.e., the adversary should be unable to detect whether or not meaningful communication is taking place, while the legitimate receiver should reconstruct any potential messages from the transmitter with high probability simultaneously. We provide inner bounds on the stealthy capacities under both adversarial erasure and adversarial overwrite jamming.

cs.IT↗

arXiv2020

OverSketched Newton: Fast Convex Optimization for Serverless Systems

Motivated by recent developments in serverless systems for large-scale computation as well as improvements in scalable randomized matrix algorithms, we develop OverSketched Newton, a randomized Hessian-based optimization algorithm to solve large-scale convex optimization problems in serverless systems. OverSketched Newton leverages matrix sketching ideas from Randomized Numerical Linear Algebra to compute the Hessian approximately. These sketching methods lead to inbuilt resiliency against stragglers that are a characteristic of serverless architectures. Depending on whether the problem is strongly convex or not, we propose different iteration updates using the approximate Hessian. For both cases, we establish convergence guarantees for OverSketched Newton and empirically validate our results by solving large-scale supervised learning problems on real-world datasets. Experiments demonstrate a reduction of ~50% in total running time on AWS Lambda, compared to state-of-the-art distributed optimization schemes.

cs.DC↗

arXiv2020

Communication-Efficient Gradient Coding for Straggler Mitigation in Distributed Learning

Distributed implementations of gradient-based methods, wherein a server distributes gradient computations across worker machines, need to overcome two limitations: delays caused by slow running machines called 'stragglers', and communication overheads. Recently, Ye and Abbe [ICML 2018] proposed a coding-theoretic paradigm to characterize a fundamental trade-off between computation load per worker, communication overhead per worker, and straggler tolerance. However, their proposed coding schemes suffer from heavy decoding complexity and poor numerical stability. In this paper, we develop a communication-efficient gradient coding framework to overcome these drawbacks. Our proposed framework enables using any linear code to design the encoding and decoding functions. When a particular code is used in this framework, its block-length determines the computation load, dimension determines the communication overhead, and minimum distance determines the straggler tolerance. The flexibility of choosing a code allows us to gracefully trade-off the straggler threshold and communication overhead for smaller decoding complexity and higher numerical stability. Further, we show that using a maximum distance separable (MDS) code generated by a random Gaussian matrix in our framework yields a gradient code that is optimal with respect to the trade-off and, in addition, satisfies stronger guarantees on numerical stability as compared to the previously proposed schemes. Finally, we evaluate our proposed framework on Amazon EC2 and demonstrate that it reduces the average iteration time by 16% as compared to prior gradient coding schemes.

cs.IT↗